Compare models
Choose two or three models, including exact thinking and fast versions. Copy the URL to share your selection.
| Comparison | Gemini 3.8 Flashgoogle/gemini-3.8-flash | Choose model 2 |
|---|---|---|
| Type | Chat | — |
| TokenBaazar price · 50% off | ₹36.00 in / ₹180.00 out per 1M tokens | — |
| Market price | ₹72.00 in / ₹360.00 out per 1M tokens | — |
| Context window (provider) | Not applicable | — |
| Input token limit (provider) | 1,048,576 tokens | — |
| Maximum output | 65,536 tokens | — |
| Vendor input modalities | Not verified | — |
| Vendor output modalities | Not verified | — |
| TokenBaazar endpoints | POST /v1/chat/completions | — |
| Benchmark evidence | 6 source-linked results | — |
| GPQA Diamond | 94.44% Vals AI independent evaluation, default model configuration, dated post-Sept 2, 2026 GA launch. Published source text: GPQA Diamond Vals AI | 94.44% | 4 of 23 | 4 of 138 | Leader Gemini 3.1 Pro | 1.01 pts behind AIEvals – Gemini 3.8 Flash benchmark results (Vals AI methodology) | — |
| SWE-bench Verified | 80% Vals AI independent evaluation, default configuration. Published source text: SWE-bench (Verified) Vals AI | 80.00% | 18 of 23 | 24 of 88 AIEvals – Gemini 3.8 Flash benchmark results (Vals AI methodology) | — |
| Terminal-Bench 2.1 | 89.4% Terminus 2 default agent harness, high effort, Sept 2026 GA launch per Google model card / Google evals-methodology page. Published source text: Terminal-Bench 2.1 89.4% (Terminus 2 harness) Wait Which Model – Gemini 3.8 Flash | — |
| Humanity's Last Exam | 54.9% High effort/thinking setting, Sept 2026 GA launch. Published source text: Humanity's Last Exam 54.9% Wait Which Model – Gemini 3.8 Flash | — |
| FrontierCode v1.1 (Extended) | 53.45% Cognition FrontierCode 1.1; Gemini 3.8 Flash; medium effort; chisel harness; Extended subset (150 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.5345. Publisher evaluation, not a TokenBazaar measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget. Cognition · FrontierCode 1.1 original leaderboard | — |
| FrontierCode v1.1 (Main) | 41.19% Cognition FrontierCode 1.1; Gemini 3.8 Flash; medium effort; chisel harness; Main subset (100 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.4119. Publisher evaluation, not a TokenBazaar measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget. Cognition · FrontierCode 1.1 original leaderboard | — |
No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenBaazar API support.
— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenBaazar media controls and response formats are listed separately.
Gemini 3.8 Flash
Sources and verification
Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.
- Provider model specifications
Vendor-reported
Last checked - AIEvals – Gemini 3.8 Flash benchmark results (Vals AI methodology)
Third-party report
Last checked - Wait Which Model – Gemini 3.8 Flash
Third-party report
Last checked - Cognition · FrontierCode 1.1 original leaderboard
Third-party report
Last checked
Research notes (1)
- Published provider limits; maximum-capacity requests have not been independently exercised through TokenBaazar. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.